MEGA-Bench - Application: Planning: leaderboard
The "Application: Planning" subtask of MEGA-Bench. TIGER-Lab multimodal evaluation with 500+ tasks across vision-language understanding, generation, and reasoning with 44 models.
Metric: Average Score (%). Source: huggingface.co. Saturation forecast: Around January 2027. 44 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 2.5 Pro (Preview 03-25) | 51.7 | #123 |
| 2 | Claude 3.5 Sonnet (20241022) | 39.9 | #291 |
| 3 | Gemini 2.0 Flash (Preview) | 36 | #370 |
| 4 | Claude 3.5 Sonnet (20240620) | 33.8 | #299 |
| 5 | Gemini 1.5 Pro (002) | 33.4 | #349 |
| 6 | GPT-4o | 33.2 | #343 |
| 7 | Qwen 2 VL 72B | 30.7 | #460 |
| 8 | GLM-4.1V-9B (Thinking) | 26.5 | #472 (GLM-4.1V-9B) |
| 9 | Gemini 1.5 Flash (002) | 26.4 | #583 |
| 10 | InternVL2.5-78B | 26.4 | #431 |
| 11 | InternVL3-78B | 25.2 | #352 |
| 12 | Gemma 3 27B (IT) | 25 | #523 |
| 13 | GPT-4o Mini | 24.2 | #599 |
| 14 | InternVL3-38B | 20 | #405 |
| 15 | InternVL3-14B | 19.6 | #505 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=mega-bench-application-planning · How It Works · Data refreshed daily, snapshot 2026-10-20.